Merge tag 'v4.4.121' into toradex_vf_4.4-nextColibri-VF_LXDE-Image_2.8b2.97-20180331

This is the 4.4.121 stable release

7 files changed, 70 insertions, 59 deletions

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 6bd2c6c95373..3f93dedb5a4d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -31,6 +31,7 @@
 
 #include <linux/linkage.h>
 #include <asm/inst.h>
+#include <asm/nospec-branch.h>
 
 /*
  * The following macros are used to move an (un)aligned 16 byte value to/from
@@ -2714,7 +2715,7 @@ ENTRY(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	call *%r11
+	CALL_NOSPEC %r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2759,7 +2760,7 @@ ENTRY(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)
 
-	call *%r11
+	CALL_NOSPEC %r11
 
 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 3633ad6145c5..c18806b5db2a 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -965,7 +965,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 
 	if (sg_is_last(req->src) &&
 	    req->src->offset + req->src->length <= PAGE_SIZE &&
-	    sg_is_last(req->dst) &&
+	    sg_is_last(req->dst) && req->dst->length &&
 	    req->dst->offset + req->dst->length <= PAGE_SIZE) {
 		one_entry_in_sg = 1;
 		scatterwalk_start(&src_sg_walk, req->src);
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index ce71f9212409..5881756f78a2 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1210,7 +1211,7 @@ camellia_xts_crypt_16way:
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;
 
-	call *%r9;
+	CALL_NOSPEC %r9;
 
 	addq $(16 * 16), %rsp;
 
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 0e0b8863a34b..0d45b04b490a 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -11,6 +11,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -1323,7 +1324,7 @@ camellia_xts_crypt_32way:
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;
 
-	call *%r9;
+	CALL_NOSPEC %r9;
 
 	addq $(16 * 32), %rsp;
 
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 4fe27e074194..48767520cbe0 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -45,6 +45,7 @@
 
 #include <asm/inst.h>
 #include <linux/linkage.h>
+#include <asm/nospec-branch.h>
 
 ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
 
@@ -172,7 +173,7 @@ continue_block:
 	movzxw  (bufp, %rax, 2), len
 	offset=crc_array-jump_table
 	lea     offset(bufp, len, 1), bufp
-	jmp     *bufp
+	JMP_NOSPEC bufp
 
 	################################################################
 	## 2a) PROCESS FULL BLOCKS:
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 4264a3d59589..7c064887b783 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -164,7 +164,6 @@ static struct shash_alg alg = {
 	.init		= poly1305_simd_init,
 	.update		= poly1305_simd_update,
 	.final		= crypto_poly1305_final,
-	.setkey		= crypto_poly1305_setkey,
 	.descsize	= sizeof(struct poly1305_simd_desc_ctx),
 	.base		= {
 		.cra_name		= "poly1305",
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index 1c3b7ceb36d2..e7273a606a07 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -55,29 +55,31 @@
 #define RAB1bl %bl
 #define RAB2bl %cl
 
+#define CD0 0x0(%rsp)
+#define CD1 0x8(%rsp)
+#define CD2 0x10(%rsp)
+
+# used only before/after all rounds
 #define RCD0 %r8
 #define RCD1 %r9
 #define RCD2 %r10
 
-#define RCD0d %r8d
-#define RCD1d %r9d
-#define RCD2d %r10d
-
-#define RX0 %rbp
-#define RX1 %r11
-#define RX2 %r12
+# used only during rounds
+#define RX0 %r8
+#define RX1 %r9
+#define RX2 %r10
 
-#define RX0d %ebp
-#define RX1d %r11d
-#define RX2d %r12d
+#define RX0d %r8d
+#define RX1d %r9d
+#define RX2d %r10d
 
-#define RY0 %r13
-#define RY1 %r14
-#define RY2 %r15
+#define RY0 %r11
+#define RY1 %r12
+#define RY2 %r13
 
-#define RY0d %r13d
-#define RY1d %r14d
-#define RY2d %r15d
+#define RY0d %r11d
+#define RY1d %r12d
+#define RY2d %r13d
 
 #define RT0 %rdx
 #define RT1 %rsi
@@ -85,6 +87,8 @@
 #define RT0d %edx
 #define RT1d %esi
 
+#define RT1bl %sil
+
 #define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \
 	movzbl ab ## bl,		tmp2 ## d; \
 	movzbl ab ## bh,		tmp1 ## d; \
@@ -92,6 +96,11 @@
 	op1##l T0(CTX, tmp2, 4),	dst ## d; \
 	op2##l T1(CTX, tmp1, 4),	dst ## d;
 
+#define swap_ab_with_cd(ab, cd, tmp)	\
+	movq cd, tmp;			\
+	movq ab, cd;			\
+	movq tmp, ab;
+
 /*
  * Combined G1 & G2 function. Reordered with help of rotates to have moves
  * at begining.
@@ -110,15 +119,15 @@
 	/* G1,2 && G2,2 */ \
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \
-	xchgq cd ## 0, ab ## 0; \
+	swap_ab_with_cd(ab ## 0, cd ## 0, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \
-	xchgq cd ## 1, ab ## 1; \
+	swap_ab_with_cd(ab ## 1, cd ## 1, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \
-	xchgq cd ## 2, ab ## 2;
+	swap_ab_with_cd(ab ## 2, cd ## 2, RT0);
 
 #define enc_round_end(ab, x, y, n) \
 	addl y ## d,			x ## d; \
@@ -168,6 +177,16 @@
 	decrypt_round3(ba, dc, (n*2)+1); \
 	decrypt_round3(ba, dc, (n*2));
 
+#define push_cd()	\
+	pushq RCD2;	\
+	pushq RCD1;	\
+	pushq RCD0;
+
+#define pop_cd()	\
+	popq RCD0;	\
+	popq RCD1;	\
+	popq RCD2;
+
 #define inpack3(in, n, xy, m) \
 	movq 4*(n)(in),			xy ## 0; \
 	xorq w+4*m(CTX),		xy ## 0; \
@@ -223,11 +242,8 @@ ENTRY(__twofish_enc_blk_3way)
 	 *	%rdx: src, RIO
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rcx; /* bool xor */
@@ -235,40 +251,36 @@ ENTRY(__twofish_enc_blk_3way)
 
 	inpack_enc3();
 
-	encrypt_cycle3(RAB, RCD, 0);
-	encrypt_cycle3(RAB, RCD, 1);
-	encrypt_cycle3(RAB, RCD, 2);
-	encrypt_cycle3(RAB, RCD, 3);
-	encrypt_cycle3(RAB, RCD, 4);
-	encrypt_cycle3(RAB, RCD, 5);
-	encrypt_cycle3(RAB, RCD, 6);
-	encrypt_cycle3(RAB, RCD, 7);
+	push_cd();
+	encrypt_cycle3(RAB, CD, 0);
+	encrypt_cycle3(RAB, CD, 1);
+	encrypt_cycle3(RAB, CD, 2);
+	encrypt_cycle3(RAB, CD, 3);
+	encrypt_cycle3(RAB, CD, 4);
+	encrypt_cycle3(RAB, CD, 5);
+	encrypt_cycle3(RAB, CD, 6);
+	encrypt_cycle3(RAB, CD, 7);
+	pop_cd();
 
 	popq RIO; /* dst */
-	popq %rbp; /* bool xor */
+	popq RT1; /* bool xor */
 
-	testb %bpl, %bpl;
+	testb RT1bl, RT1bl;
 	jnz .L__enc_xor3;
 
 	outunpack_enc3(mov);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 
 .L__enc_xor3:
 	outunpack_enc3(xor);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(__twofish_enc_blk_3way)
 
@@ -278,35 +290,31 @@ ENTRY(twofish_dec_blk_3way)
 	 *	%rsi: dst
 	 *	%rdx: src, RIO
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rsi; /* dst */
 
 	inpack_dec3();
 
-	decrypt_cycle3(RAB, RCD, 7);
-	decrypt_cycle3(RAB, RCD, 6);
-	decrypt_cycle3(RAB, RCD, 5);
-	decrypt_cycle3(RAB, RCD, 4);
-	decrypt_cycle3(RAB, RCD, 3);
-	decrypt_cycle3(RAB, RCD, 2);
-	decrypt_cycle3(RAB, RCD, 1);
-	decrypt_cycle3(RAB, RCD, 0);
+	push_cd();
+	decrypt_cycle3(RAB, CD, 7);
+	decrypt_cycle3(RAB, CD, 6);
+	decrypt_cycle3(RAB, CD, 5);
+	decrypt_cycle3(RAB, CD, 4);
+	decrypt_cycle3(RAB, CD, 3);
+	decrypt_cycle3(RAB, CD, 2);
+	decrypt_cycle3(RAB, CD, 1);
+	decrypt_cycle3(RAB, CD, 0);
+	pop_cd();
 
 	popq RIO; /* dst */
 
 	outunpack_dec3();
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(twofish_dec_blk_3way)